anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
2,144 Commits 235 Branches 31 Tags
df8137e858233685407ec266b3a6c8b030d99f30
Commit Graph
954 Commits
Author SHA1 Message Date
Sy03 df8137e858 Address Qwen3-TTS payload split review comments 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-07-04 16:21:02 +08:00
Yueqian Lin ede3dddfdf fix(serving): scope no-async-chunk FINAL_ONLY streaming to qwen3_tts 
async_chunk defaults to False in OmniModelConfig, so coercing every
async_chunk=False deploy to FINAL_ONLY for streaming requests would
silently disable incremental delivery for non-Qwen3 models that stream
DELTA-style today. Gate the coercion on _tts_model_type == "qwen3_tts"
(the model this PR validated) and pin the non-qwen3 behavior with a test.

Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-07-03 22:57:27 -07:00
Gao Han fc40c1b236 Merge branch 'main' into bugfix/qwen3-tts-customvoice-asr-escalation 2026-07-04 13:26:03 +08:00
Sy03 c523026a8e Fix Qwen3-TTS no-async-chunk payload splitting 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-07-04 12:35:08 +08:00
CAICAII 51c14eeaed [BugFix] Preserve explicit deploy stage engine_extras (#4255) 
Signed-off-by: CAICAIIs <3360776475@qq.com>
 2026-07-04 04:16:21 +00:00
Haco f7cdc45977 [BugFix] deploy schema stage runtime overrides for CLI diffusion flags no longer works (#4101) 
Signed-off-by: xiaohajiayou <923390377@qq.com>
 2026-07-04 03:17:25 +00:00
Kotaro Kikuchi 46f10478dc [Bugfix] Qwen-Image-Layered: allow layers=2 to match upstream demo (#4777) 
Signed-off-by: Kotaro Kikuchi <ktrk115@gmail.com>
 2026-07-04 03:06:24 +00:00
Canlin Guo a8b2bf11d2 [Feature] Support MOSS-TTS-Local-v1.5 Streaming (#4804) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2026-07-03 16:00:30 +08:00
Aleksi VesantoandWeiQing Chen 0455bffc37 [ROCm][Perf] Add ROCm support for MXFP4 (w4a4) online quantization (#4104) 
Signed-off-by: Aleksi Vesanto <avesanto@amd.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
 2026-07-03 13:17:32 +08:00
akshatvishu 04f400d36c [Bugfix] Report stepwise Qwen-Image profiler metrics (#4517) 
Signed-off-by: akshatvishu <akshatnayak197@gmail.com>
 2026-07-03 04:32:22 +00:00
wangyu 0b59dfb94a [Bugfix] Fix pytest 9.1.0 duplicate parametrization in run_benchmark.py (#4784) 
Signed-off-by: wangyu <410167048@qq.com>
 2026-07-03 04:15:32 +00:00
akshatvishu d9cf85d5e2 [BugFix] Use KV cache scale mapper in custom loaders (#4810) 
Signed-off-by: akshatvishu <akshatnayak197@gmail.com>
 2026-07-03 04:11:28 +00:00
Mu GuanLin 3023bc40c2 [Feature][Refactor] LTX-2.3 I2V Support, Public Examples, and Shared Pipeline Refactor (#4739) 
Signed-off-by: mglyn <1203789601@qq.com>
 2026-07-03 11:29:22 +08:00
CAICAII b443504d61 [Diffusion] Add Diffusers quantization config bridge (#3837) 
Signed-off-by: CAICAIIs <3360776475@qq.com>
 2026-07-03 03:06:44 +00:00
Jiaqian Liu f00caf35c4 [image][bugfix] Fix HunyuanImage3 bridge request batching (#4849) 
Signed-off-by: Celeste-jq <591998922@qq.com>
 2026-07-03 02:58:13 +00:00
Sean Gillen 431a7c71ac [Model] Cosmos3: Skip unused action conditioning frames (#4789) 
Signed-off-by: Sean Gillen <sgillen@nvidia.com>
 2026-07-03 01:45:44 +00:00
Jun Hee YooandClaude Opus 4.8 9d8089095e [Bugfix] Support append/extend/count actions in TrackingArgumentParser (#4639) 
Signed-off-by: Junhee Yoo <junhee.yoo@navercorp.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-07-02 23:29:24 +00:00
Zeyu Huang | 黃澤宇andHongsheng Liu 1b0de21c55 [Chore]: refactor out unused/redundant params in diffusion pipelines (#1235) 
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-07-02 16:32:05 +02:00
Alex Brooks 5c51782c6b [Bugfix] Realign Serving Tokenization Name to Fix Error Handling Routes (#4816) 
Signed-off-by: Alex Brooks <albrooks@redhat.com>
 2026-07-02 15:23:35 +08:00
Sy03Claude Sonnet 4.6Yueqian Lin
 		f11b32a42e [Bugfix] Qwen3-TTS talker handles multi-token replay on resume (#4559) 
Signed-off-by: Sy03 <1370724210@qq.com>
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-07-02 04:46:05 +00:00
Jiaqian Liu a25636d780 [NPU] Fix HunyuanImage3 MoE EP+SP parallel mapping (#4344) 
Signed-off-by: Celeste-jq <591998922@qq.com>
 2026-07-02 04:14:12 +00:00
NumberWanandCursor bbc0476237 [CI] Lower Qwen-Image e2e SSIM threshold from 0.97 to 0.94 (#4613) 
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-02 02:22:10 +00:00
ChenWenjing 720bd756bf [ci]loose voxcpm2 HNR baseline (#4801) 
Signed-off-by: CHEN <116010019@link.cuhk.edu.cn>
 2026-07-02 02:19:05 +00:00
xinlongClaude Opus 4.8amy-why-3459
 		4d2ee15156 [BugFix] Fix Code2Wav async_chunk streaming tail drop (boundary clicks + ~1.2% time compression) (#4706) 
Signed-off-by: zhuxinlong <zhuxinlong959@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-07-02 09:13:42 +08:00
Thanaji Rao Thakkalapelli 1788d76eb3 [Feature] Improve diffusion LoRA compatibility for SDXL (#4825) 
Signed-off-by: Thanaji Rao Thakkalapelli <thanaji.rao.thakkalapelli@intel.com>
 2026-07-01 23:41:16 +00:00
Alex BrooksandDidan Deng d526dc93e8 [Fix]: Set .transformer on SenseNova pipeline, warn if no .transformer in CacheDiT summary (#4326) 
Signed-off-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
 2026-07-01 17:40:07 +00:00
Renzheng Wang 6b11f6b41d [Bugfix][Quant] Gate quack FP8 to datacenter Blackwell (sm_100.x) only (#4817) 
Signed-off-by: wangrzneu <wangrzneu@gmail.com>
 2026-07-01 16:51:17 +00:00
Zhou Taichang a560ed184d [Rebase] Rebase to vllm v0.24.0 (#4709) 2026-06-30 19:41:06 +08:00
SYLAR bb8614595d [BugFix][Cosmos3] Pad sound latents so video+sound runs under sequence parallelism (#4678) 
Signed-off-by: lishunyang12 <125541396+lishunyang12@users.noreply.github.com>
Signed-off-by: lishunyang <lishunyang12@163.com>
 2026-06-30 17:23:36 +08:00
boatman 4028680b7e [Perf]: Fused RMSNorm+3D Rope kernel in Sensenova-U1 (#4669) 
Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>
 2026-06-30 16:32:47 +08:00
Yi LiuandCopilot 99234881f5 [Quant][AutoRound] Add W4A16 support for Qwen-Image (#3588) 
Signed-off-by: yiliu30 <yi4.liu@intel.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
 2026-06-30 16:27:28 +08:00
boatmansphinxkkkbc汪志鹏
 		dd3a4d0a29 [Feat] Support CFG-Parallel For Sensenova-U1-8B-MoT (#4188) 
Signed-off-by: sphinxkkkbc <binchengkang8@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: sphinxkkkbc <binchengkang8@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
 2026-06-30 08:03:26 +00:00
Jae 0899a1a666 Migrate audiox examples (#4607) 
Signed-off-by: zzehli <jaeli_ottawa@outlook.com>
 2026-06-30 04:41:30 +00:00
Mohammed Saif AbedandClaude 2fc00efa49 [Model] Migrate MammothModa2-Preview example to standard task example + model_extras (#4691) 
Signed-off-by: mo saif <moisf56@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-06-30 04:34:06 +00:00
faceless void 11f6a0b72e Make speech streaming default to SSE (#4679) 
Signed-off-by: syd520zy <529477025@qq.com>
 2026-06-30 02:17:24 +00:00
JiangJie ZhangandSamit c45ac74d43 [Core][Frontend] Support request-level batching for diffusion pipelines (#4079) 
Signed-off-by: jader <yjader@foxmail.com>
Co-authored-by: Samit <285365963@qq.com>
 2026-06-29 18:09:19 +02:00
Peiqi YinChenguang ZHENGCursorHongsheng LiuGao Han
 		504698dec8 [Core] Performance fix for orchestrator bottleneck: separates inter-stage from client outputs (#4527) 
Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
Co-authored-by: Chenguang ZHENG <645327136@qq.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
 2026-06-29 17:43:36 +02:00
wangyuandHongsheng Liu 7619ed6b82 [CI] Reducing mithril-h100-pool in ready&merge CI, optimize ready CI duration (#4354) 
Signed-off-by: [Your Name] <your.email@example.com>
Signed-off-by: wangyu <410167048@qq.com>
Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: [Your Name] <[Your Email]>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-29 05:17:57 +00:00
Isaac Hung e9d4931781 [Core] Remove dead custom_process_input_func hooks in stage input processors (#4531) 
Signed-off-by: Isaac Hung <manhei5001@gmail.com>
 2026-06-29 05:17:25 +02:00
bjf-frzandAlicia cd35572069 [CI]Add Cosmos3 L2 serving tests (#4535) 
Signed-off-by: bjf-frz <frz123db@gmail.com>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
 2026-06-29 09:15:17 +08:00
Chendi.Xue 60ccadfbb6 [WAN_S2V] Enable HSDP for wan s2v (#4458) 
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
 2026-06-28 06:27:58 +02:00
Yueqian Lin 92f7208559 [Bugfix] CosyVoice3: wrap ref_text in instruction template (#4644) (#4756) 2026-06-27 14:38:33 -07:00
Yueqian Lin 05a86ed10e [Test] Un-skip Qwen3-TTS batch E2E; match documented omit-null response shape (#4757) (#4759) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-06-26 23:31:44 -07:00
wangyu c6ee3f7c18 [Test] Skip Qwen3-TTS batch E2E tests (#4758) 2026-06-27 10:45:40 +08:00
Rahul SteigerandHongsheng Liu 327e9dcaf2 [Feature] Spatially-sharded (SP) decode for the Wan VAE (#4620) 
Signed-off-by: Rahul Steiger <rsteiger@nvidia.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-27 09:01:25 +08:00
Yueqian LinandSy03 b66cd024b9 [Bugfix] Fix /v1/audio/speech usage token accounting for Qwen3-TTS (#4646) (#4673) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Sy03 <1370724210@qq.com>
 2026-06-27 06:13:31 +08:00
Gao Han c582805e7a Revert "[Bugfix] Use MediaConnector for image/video URL fetching to prevent SSRF" (#4751) 2026-06-27 01:18:48 +08:00
Sy03 c39ac9fffd [Bugfix] Stream Qwen3-TTS WebSocket input as one request (#4731) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-06-26 07:48:30 +00:00
Yuanheng Zhao 580a0efe40 [Bugfix] Add back resolving from deploy config written pipeline in StageConfigFactory (#4729) 
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
 2026-06-25 22:11:49 -06:00
bmengkeandHongsheng Liu 329c98ff9d Wan2.2: Fix the bug of using cache-dit with ulysses in t2v and i2v (#3927) 
Signed-off-by: Mengkejiergeli Ba <mengkejiergeli.ba@intel.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-25 15:15:59 +00:00